
agentZ
Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.

Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.

Let your AI go full send. Your home directory stays home.

JIT-based userspace Linux kernel that runs containers natively on Apple Silicon macOS without a VM. Drop-in Docker Engine API replacement with…

Linux application sandboxing and distribution framework

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

Run Windows inside a Docker container with KVM acceleration, automatic installation, and customizable resources. Supports multiple Windows versions,…

A security-focused library OS supporting kernel- and user-mode execution

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

A secure low code deception runtime framework, leveraging AI for System Virtualization.

Run Firefox in a rootless Podman container with dropped capabilities, isolated networking, and ephemeral storage to contain sandbox escapes and…

Microsoft's curated repository of secure boot objects (KeK, Db, Dbx) for firmware and runtime, enabling transparent revocation updates and…


A local sandbox for your AI agents

Ephemeral microVM sandbox for AI agents with network allowlisting, secret injection via MITM proxy, and VM-level isolation. Boots in under a second,…

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running…

Manage OpenClaw in your team (Enterprise) by providing it compute infrastructure, tool integration, Authentication and security primitives